{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.48709848523139954, "min": 0.48709848523139954, "max": 1.4230228662490845, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14379.1474609375, "min": 14379.1474609375, "max": 43168.8203125, "count": 33 }, "Pyramids.Step.mean": { "value": 989908.0, "min": 29952.0, "max": 989908.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989908.0, "min": 29952.0, "max": 989908.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3390501141548157, "min": -0.11158458143472672, "max": 0.5423669815063477, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 88.83113098144531, "min": -26.891883850097656, "max": 149.6932830810547, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.015652049332857132, "min": -0.015652049332857132, "max": 0.6612074375152588, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -4.100836753845215, "min": -4.100836753845215, "max": 156.70616149902344, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06794009114237676, "min": 0.06319900075045769, "max": 0.07414390436058645, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9511612759932746, "min": 0.4909359239546606, "max": 1.077392830494015, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011806849425160314, "min": 0.00010038182971909481, "max": 0.015531748532278773, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1652958919522444, "min": 0.0013049637863482325, "max": 0.2329762279841816, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.691518864764288e-06, "min": 7.691518864764288e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010768126410670004, "min": 0.00010768126410670004, "max": 0.0033821492726170002, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256380714285715, "min": 0.10256380714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358933, "min": 1.3886848, "max": 2.527383, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026612433357142863, "min": 0.00026612433357142863, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003725740670000001, "min": 0.003725740670000001, "max": 0.11276556170000003, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006218408700078726, "min": 0.006218408700078726, "max": 0.4819709360599518, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08705772459506989, "min": 0.08705772459506989, "max": 3.3737964630126953, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 473.03076923076924, "min": 357.4634146341463, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30747.0, "min": 15984.0, "max": 32945.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2733030968811363, "min": -1.0000000521540642, "max": 1.5799333127658992, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 81.49139820039272, "min": -32.000001668930054, "max": 132.71439827233553, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2733030968811363, "min": -1.0000000521540642, "max": 1.5799333127658992, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 81.49139820039272, "min": -32.000001668930054, "max": 132.71439827233553, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.031235218680578214, "min": 0.026781150028390193, "max": 10.54713105224073, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 1.9990539955570057, "min": 1.812997774570249, "max": 168.75409683585167, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1746827599", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1746829654" }, "total": 2055.03118168, "count": 1, "self": 0.6408581609998691, "children": { "run_training.setup": { "total": 0.024888895000003686, "count": 1, "self": 0.024888895000003686 }, "TrainerController.start_learning": { "total": 2054.365434624, "count": 1, "self": 1.3998692729742288, "children": { "TrainerController._reset_env": { "total": 3.9588104349999185, "count": 1, "self": 3.9588104349999185 }, "TrainerController.advance": { "total": 2048.9305513090253, "count": 63547, "self": 1.5014867919994686, "children": { "env_step": { "total": 1378.5312462880133, "count": 63547, "self": 1225.8090279279772, "children": { "SubprocessEnvManager._take_step": { "total": 151.92064938400006, "count": 63547, "self": 4.576233437970814, "children": { "TorchPolicy.evaluate": { "total": 147.34441594602924, "count": 62571, "self": 147.34441594602924 } } }, "workers": { "total": 0.8015689760360374, "count": 63547, "self": 0.0, "children": { "worker_root": { "total": 2049.5872459120105, "count": 63547, "is_parallel": true, "self": 936.437813883949, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005582172999993418, "count": 1, "is_parallel": true, "self": 0.004059480000023541, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015226929999698768, "count": 8, "is_parallel": true, "self": 0.0015226929999698768 } } }, "UnityEnvironment.step": { "total": 0.05015736600000764, "count": 1, "is_parallel": true, "self": 0.0005641110000169647, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044955800001389434, "count": 1, "is_parallel": true, "self": 0.00044955800001389434 }, "communicator.exchange": { "total": 0.04550233700001627, "count": 1, "is_parallel": true, "self": 0.04550233700001627 }, "steps_from_proto": { "total": 0.003641359999960514, "count": 1, "is_parallel": true, "self": 0.0023991519999526645, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012422080000078495, "count": 8, "is_parallel": true, "self": 0.0012422080000078495 } } } } } } }, "UnityEnvironment.step": { "total": 1113.1494320280615, "count": 63546, "is_parallel": true, "self": 32.06786327802524, "children": { "UnityEnvironment._generate_step_input": { "total": 22.39015227600089, "count": 63546, "is_parallel": true, "self": 22.39015227600089 }, "communicator.exchange": { "total": 965.7642233239986, "count": 63546, "is_parallel": true, "self": 965.7642233239986 }, "steps_from_proto": { "total": 92.92719315003671, "count": 63546, "is_parallel": true, "self": 18.72022538102067, "children": { "_process_rank_one_or_two_observation": { "total": 74.20696776901605, "count": 508368, "is_parallel": true, "self": 74.20696776901605 } } } } } } } } } } }, "trainer_advance": { "total": 668.8978182290126, "count": 63547, "self": 2.5973357819730154, "children": { "process_trajectory": { "total": 126.9322766270368, "count": 63547, "self": 126.6905785990366, "children": { "RLTrainer._checkpoint": { "total": 0.2416980280002008, "count": 2, "self": 0.2416980280002008 } } }, "_update_policy": { "total": 539.3682058200028, "count": 442, "self": 298.40969907501324, "children": { "TorchPPOOptimizer.update": { "total": 240.95850674498956, "count": 22824, "self": 240.95850674498956 } } } } } } }, "trainer_threads": { "total": 8.750002962187864e-07, "count": 1, "self": 8.750002962187864e-07 }, "TrainerController._save_models": { "total": 0.07620273200018346, "count": 1, "self": 0.001317427000230964, "children": { "RLTrainer._checkpoint": { "total": 0.0748853049999525, "count": 1, "self": 0.0748853049999525 } } } } } } }